AMR-to-text Generation with Synchronous Node Replacement Grammar
Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, Daniel Gildea · 2017
This paper addresses the task of AMR-totext generation by leveraging synchronous node replacement grammar.During training, graph-to-string rules are learned using a heuristic extraction algorithm.At test time, a graph transducer is applied to collapse input AMRs and generate output sentences.Evaluated on a standard benchmark, our method gives the state-of-the-art result.